Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Applications
Type
ArticleKAUST Department
Computer Science ProgramComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Extreme Computing Research Center
Visual Computing Center (VCC)
Date
2018-10-02Online Publication Date
2018-10-02Print Publication Date
2018-01Permanent link to this record
http://hdl.handle.net/10754/631138
Metadata
Show full item recordAbstract
We propose a stochastic extension of the primal-dual hybrid gradient algorithm studied by Chambolle and Pock in 2011 to solve saddle point problems that are separable in the dual variable. The analysis is carried out for general convex-concave saddle point problems and problems that are either partially smooth / strongly convex or fully smooth / strongly convex. We perform the analysis for arbitrary samplings of dual variables, and we obtain known deterministic results as a special case. Several variants of our stochastic method significantly outperform the deterministic variant on a variety of imaging tasks.Citation
Chambolle A, Ehrhardt MJ, Richtárik P, Schönlieb C-B (2018) Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Applications. SIAM Journal on Optimization 28: 2783–2808. Available: http://dx.doi.org/10.1137/17M1134834.Sponsors
The work of the first author was supported by the ANR, 'EANOI' project I1148 / ANR-12-IS01-0003 (joint with FWF); part of this work was done while he was hosted in Churchill College and DAMTP, Centre for Mathematical Sciences, University of Cambridge, thanks to support from the French Embassy in the UK and the Cantab Capital Institute for the Mathematics of Information. The work of the second and fourth authors was supported by Leverhulme Trust project ``Breaking the non-convexity barrier,"" EPSRC grant EP/M00483X/1, EPSRC centre grant EP/N014588/1, the Cantab Capital Institute for the Mathematics of Information, and from CHiPS (Horizon 2020 RISE project grant). The second author carried out initial work supported by the EPSRC platform grant EP/M020533/1. Moreover, the fourth author is thankful for support by The Alan Turing Institute. The work of the third author was supported by EPSRC Fellowship in Mathematical Sciences grant EP/N005538/1, entitled ``Randomized algorithms for extreme convex optimization.""Journal
SIAM Journal on OptimizationAdditional Links
https://epubs.siam.org/doi/10.1137/17M1134834ae974a485f413a2113503eed53cd6c53
10.1137/17M1134834
Scopus Count
Except where otherwise noted, this item's license is described as Published by SIAM under the terms of the Creative Commons 4.0 license